AI-Assisted Test Execution as an Augmentation Layer in Enterprise Quality Engineering

Abstract

Artificial intelligence has introduced new capabilities for enterprise quality engineering, yet the absence of structured governance frameworks limits its practical adoption in regulated software environments. This paper presents the Probabilistic Augmentation and Governance Model (PAGM), a three-tier framework that formally allocates responsibility between AI agents and human testers across autonomous execution, confidence-gated escalation, and human-led verification. PAGM draws on a structured review of literature spanning AI quality assurance, autonomous system testing, UI-resilient automation, explainable AI, and defect prediction to identify governance gaps in existing approaches. The model addresses eight documented AI testing challenges, including interpretability, absence of formal specifications, oracle determination, and dynamic operational environments. Unlike prior approaches that treat AI test execution as a performance optimization problem, PAGM positions governance, traceability, and bounded autonomy as first-class design requirements. Its application is demonstrated through a regulated property insurance release pipeline in which PAGM enables a full quarterly regression cycle within a five-day service level agreement while preserving mandatory human accountability for premium calculation and claims adjudication workflows. Quantitative evidence from the literature supports the model's constituent mechanisms, including a 95% UI change handling rate for contextual recognition methods compared to 40 to 80 percent achieved by conventional tools and AI-based classifiers outperforming classical approaches by 25 to 50 percent across software quality metrics. PAGM provides a governance-ready foundation for organizations seeking to deploy AI-assisted testing at enterprise scale within regulated or auditable environments.